by Professor Dato Dr. Ahmad Ibrahim,
Sustainability is no longer alien to many. Messages on sustainability appear regularly in the world media. We have been warned of the threats to global well-being posed by our unsustainable lifestyle. Climate change is one threat that drives world commitment to sustainability. Among measures to drive sustainability are those encapsulated in the UN-SDGs. Many have become familiar with the 17 Goals of the SDGs. All countries have accepted the SDGs as guide for national commitments. At UCSI university, education in sustainable development, ESD, is now incorporated, as a matter of policy, in all the university courses. Most, if not all, countries around the world are actively implementing their policies on sustainability, taking into account their unique local situation.
As in most policies, implementation has always been the biggest challenge. A robust implementation regime which includes an effective monitoring and reporting system is critical. It is only through such monitoring and evaluation that we get feedbacks to improve. Admittedly, the accurate measurement of the policy outcomes is important. We need reliable measures to effectively monitor the progress of the sustainability goals. Only then can we better decide on the necessary interventions to improve the outcomes. The traditional approaches to measure outcomes rely on household surveys, which are often conducted infrequently. Those prove to be less accurate.
The rapidly growing abundance and quality of satellite imagery has emerged as a better option to measure such outcomes. Arising from the multiple satellite sensors launched in recent years, we can now access timely information on changes happening on the Earth’s surface. There are many reports on the use of satellite imagery to measure and understand various outcomes related to sustainable development. The use of artificial intelligence, AI, to decipher the images is seen as the gamechanger. A particular attention is given to recent machine learning–based approaches. The performance of these approaches have already been tested in smallholder agriculture, economic livelihoods, population, and informal settlements. The satellite-based performance in predicting these outcomes is shown to be strong and improving.
I recently moderated a panel discussion on the subject, hosted by CONFEXHUB and The Planet company. It became clear from the experiences shared by the panellists that the use of the latest satellite imagery technology is still in its infancy here. But the potential is substantial as we struggle to effectively monitor our initiatives on sustainability. These include the monitoring of illegal logging, river basin pollution and environmental incursions. The largest constraint to satellite based model performance is however what is called the training data for the necessary machine learning algorithm. The scarcity and frequent unreliability of ground data make both training and validation of satellite-based models difficult. Expanding the quantity and quality of such data will quickly accelerate progress in this field.
Nevertheless, despite the current and future promise of satellite-based approaches, these approaches will amplify rather than replace existing ground-based data collection efforts. Satellite imagery of the world is collected daily and can provide many useful insights into what is happening on the ground. The UN has estimated that approximately 20% of the SDG indicators can be interpreted and measured either through direct use of geospatial data itself or through integration with statistical data. In order to derive insights from satellite imagery, we must first process the imagery into a data product that is meaningful with respect to the problems that we want to solve. This is where AI is needed.
The data obtained is useful in downstream sustainability applications, such as planning riparian buffer repair projects. However, it is also extremely costly to create manually. There are efforts to advance machine learning techniques in order to derive useful insights from satellite imagery, with the goal of tackling pressing problems in the area of computational sustainability. Currently the imagery used by agencies like NADMA in the country is a few months old. So far, only government agencies use satellite imagery as part of their monitoring and early warning activities. The vast potential of satellite imagery in the plantation sector, for example, is yet to be fully realised. Not to mention the efficient survellance of illegal border crossing.
No comments:
Post a Comment